1 Showcasing RRPlots

1.0.1 Libraries

library(survival)
library(FRESA.CAD)
## Loading required package: Rcpp
## Loading required package: stringr
## Loading required package: miscTools
## Loading required package: Hmisc
## 
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:base':
## 
##     format.pval, units
## Loading required package: pROC
## Type 'citation("pROC")' for a citation.
## 
## Attaching package: 'pROC'
## The following objects are masked from 'package:stats':
## 
##     cov, smooth, var
#source("~/GitHub/FRESA.CAD/R/RRPlot.R")
#source("~/GitHub/FRESA.CAD/R/PoissonEventRiskCalibration.R")
op <- par(no.readonly = TRUE)
pander::panderOptions('digits', 3)
#pander::panderOptions('table.split.table', 400)
pander::panderOptions('keep.trailing.zeros',TRUE)
layout(matrix(1:1, nrow=1))

1.0.2 Wisconsin Data Set

dataBreast <- read.csv("~/GitHub/RISKPLOTS/DATA/wpbc.data", header=FALSE)
table(dataBreast$V2)
## 
##   N   R 
## 151  47
rownames(dataBreast) <- dataBreast$V1
dataBreast$V1 <- NULL
dataBreast$status <- 1*(dataBreast$V2=="R")
dataBreast$V2 <- NULL
dataBreast$time <- dataBreast$V3
dataBreast$V3 <- NULL
dataBreast <- sapply(dataBreast,as.numeric)
## Warning in lapply(X = X, FUN = FUN, ...): NAs introduced by coercion
dataBreast <- as.data.frame(dataBreast[complete.cases(dataBreast),])
table(dataBreast$status)
## 
##   0   1 
## 148  46

1.1 Exploring Raw Features with RRPlot

convar <- colnames(dataBreast)[lapply(apply(dataBreast,2,unique),length) > 10]
convar <- convar[convar != "time"]
topvar <- univariate_BinEnsemble(dataBreast[,c("status",convar)],"status")
pander::pander(topvar)
V35 V24 V34 V7 V16 V14 V17
0.0261 0.0261 0.0261 0.0623 0.126 0.126 0.126 
topv <- min(5,length(topvar))
topFive <- names(topvar)[1:topv]
RRanalysis <- list();
idx <- 1
for (topf in topFive)
{
  RRanalysis[[idx]] <- RRPlot(cbind(dataBreast$status,dataBreast[,topf]),
                              atProb=c(0.90),
                  timetoEvent=dataBreast$time,
                  title=topf,
#                  plotRR=FALSE
                  )
  idx <- idx + 1
}

names(RRanalysis) <- topFive

1.2 Reporting the Metrics

ROCAUC <- NULL
CstatCI <- NULL
RRatios <- NULL
LogRangp <- NULL
Sensitivity <- NULL
Specificity <- NULL

for (topf in topFive)
{
  CstatCI <- rbind(CstatCI,RRanalysis[[topf]]$c.index$cstatCI)
  RRatios <- rbind(RRatios,RRanalysis[[topf]]$RR_atP)
  LogRangp <- rbind(LogRangp,RRanalysis[[topf]]$surdif$pvalue)
  Sensitivity <- rbind(Sensitivity,RRanalysis[[topf]]$ROCAnalysis$sensitivity)
  Specificity <- rbind(Specificity,RRanalysis[[topf]]$ROCAnalysis$specificity)
  ROCAUC <- rbind(ROCAUC,RRanalysis[[topf]]$ROCAnalysis$aucs)
}
rownames(CstatCI) <- topFive
rownames(RRatios) <- topFive
rownames(LogRangp) <- topFive
rownames(Sensitivity) <- topFive
rownames(Specificity) <- topFive
rownames(ROCAUC) <- topFive

pander::pander(ROCAUC)
  est lower upper
V35 0.679 0.596 0.762
V24 0.633 0.542 0.724
V34 0.659 0.572 0.745
V7 0.610 0.515 0.705
V16 0.598 0.504 0.692 
pander::pander(CstatCI)
  mean.C Index median lower upper
V35 0.656 0.657 0.578 0.740
V24 0.677 0.679 0.596 0.757
V34 0.656 0.656 0.584 0.723
V7 0.666 0.668 0.584 0.746
V16 0.614 0.614 0.520 0.702 
pander::pander(RRatios)
  est lower upper
V35 1.37 0.698 2.69
V24 1.93 1.122 3.31
V34 1.44 0.741 2.82
V7 1.37 0.700 2.69
V16 1.04 0.462 2.32 
pander::pander(LogRangp)
V35 0.16213
V24 0.00331
V34 0.37299
V7 0.03818
V16 0.50639 
pander::pander(Sensitivity)
  est lower upper
V35 0.152 0.0634 0.289
V24 0.239 0.1259 0.388
V34 0.152 0.0634 0.289
V7 0.152 0.0634 0.289
V16 0.109 0.0362 0.236 
pander::pander(Specificity)
  est lower upper
V35 0.899 0.838 0.942
V24 0.899 0.838 0.942
V34 0.899 0.838 0.942
V7 0.899 0.838 0.942
V16 0.899 0.838 0.942 
meanMatrix <- cbind(ROCAUC[,1],CstatCI[,1],Sensitivity[,1],Specificity[,1],RRatios[,1])
colnames(meanMatrix) <- c("ROCAUC","C-Stat","Sen","Spe","RR")
pander::pander(meanMatrix)
  ROCAUC C-Stat Sen Spe RR
V35 0.679 0.656 0.152 0.899 1.37
V24 0.633 0.677 0.239 0.899 1.93
V34 0.659 0.656 0.152 0.899 1.44
V7 0.610 0.666 0.152 0.899 1.37
V16 0.598 0.614 0.109 0.899 1.04

1.3 Modeling

ml <- BSWiMS.model(Surv(time,status)~1,data=dataBreast,NumberofRepeats = 10)

[+++++++++++++++++++++++++++++++++++++++++++++++++++]…..

sm <- summary(ml)
pander::pander(sm$coefficients)
Table continues below
  Estimate lower HR upper u.Accuracy r.Accuracy
V24 5.11e-02 1.02 1.05 1.09 0.598 0.257
V26 4.62e-03 1.00 1.00 1.01 0.593 0.318
V27 2.17e-04 1.00 1.00 1.00 0.608 0.282
V34 1.30e-02 1.00 1.01 1.02 0.634 0.252
V7 5.62e-08 1.00 1.00 1.00 0.588 0.237
V35 4.49e-03 1.00 1.00 1.01 0.727 0.598
Table continues below
  full.Accuracy u.AUC r.AUC full.AUC IDI NRI z.IDI
V24 0.598 0.609 0.506 0.609 0.0619 0.436 2.86
V26 0.597 0.598 0.523 0.601 0.0624 0.398 2.76
V27 0.609 0.608 0.513 0.607 0.0562 0.434 2.76
V34 0.633 0.618 0.504 0.617 0.0317 0.470 2.41
V7 0.588 0.595 0.500 0.595 0.0487 0.380 2.30
V35 0.613 0.641 0.603 0.609 0.0279 0.551 2.25
  z.NRI Delta.AUC Frequency
V24 2.66 0.10349 1.0
V26 2.41 0.07766 1.0
V27 2.63 0.09444 1.0
V34 2.85 0.11253 1.0
V7 2.30 0.09489 0.8
V35 3.41 0.00556 1.0

1.4 Cox Model Performance

Here we evaluate the model using the RRPlot() function.

1.4.1 The evaluation of the raw Cox model with RRPlot()

Here we will use the predicted event probability assuming a baseline hazard for events withing 5 years

index <- predict(ml,dataBreast)
timeinterval <- 2*mean(subset(dataBreast,status==1)$time)

h0 <- sum(dataBreast$status & dataBreast$time <= timeinterval)
h0 <- h0/sum((dataBreast$time > timeinterval) | (dataBreast$status==1))
pander::pander(t(c(h0=h0,timeinterval=timeinterval)),caption="Initial Parameters")
Initial Parameters
h0 timeinterval
0.323 51.1 
rdata <- cbind(dataBreast$status,ppoisGzero(index,h0))
rownames(rdata) <- rownames(dataBreast)

rrAnalysisTrain <- RRPlot(rdata,atProb=c(0.90,0.80),
                     timetoEvent=dataBreast$time,
                     title="Raw Train: Breast Cancer",
                     ysurvlim=c(0.00,1.0),
                     riskTimeInterval=timeinterval)

1.4.2 Uncalibrated Performance Report

pander::pander(t(rrAnalysisTrain$OERatio),caption="O/E Ratio")
O/E Ratio
est lower upper
0.844 0.618 1.13 
pander::pander(t(rrAnalysisTrain$OE95ci),caption="O/E Ratio")
O/E Ratio
mean 50% 2.5% 97.5%
1.02 1.02 0.966 1.07 
pander::pander(t(rrAnalysisTrain$OAcum95ci),caption="O/Acum Ratio")
O/Acum Ratio
mean 50% 2.5% 97.5%
0.803 0.802 0.795 0.812 
pander::pander(rrAnalysisTrain$c.index$cstatCI,caption="C. Index")
mean.C Index median lower upper
0.683 0.683 0.604 0.762 
pander::pander(t(rrAnalysisTrain$ROCAnalysis$aucs),caption="ROC AUC")
ROC AUC
est lower upper
0.643 0.551 0.734 
pander::pander((rrAnalysisTrain$ROCAnalysis$sensitivity),caption="Sensitivity")
Sensitivity
est lower upper
0.239 0.126 0.388 
pander::pander((rrAnalysisTrain$ROCAnalysis$specificity),caption="Specificity")
Specificity
est lower upper
0.899 0.838 0.942 
pander::pander(t(rrAnalysisTrain$thr_atP),caption="Probability Thresholds")
Probability Thresholds
90% 80%
0.431 0.36 
pander::pander(t(rrAnalysisTrain$RR_atP),caption="Risk Ratio")
Risk Ratio
est lower upper
2.13 1.25 3.62 
pander::pander(rrAnalysisTrain$surdif,caption="Logrank test")
Logrank test Chisq = 11.354656 on 2 degrees of freedom, p = 0.003423
  N Observed Expected (O-E)^2/E (O-E)^2/V
class=0 147 29 36.99 1.725 8.974
class=1 21 6 4.41 0.573 0.643
class=2 26 11 4.60 8.896 9.982